Skip to content
conftrace_
2024 ICML ICML 2024

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning and Robotics

Authors

Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daume III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang

Topics

Machine Learning > Learning Types > Self-Supervised Learning Reinforcement Learning > Methods > Policy Learning Robotics > Capabilities > Manipulation

Keywords

pretraining continuous control multi-task representation few-shot policy learning negative example sampling temporal action contrastive loss
Download PDF